Nano Banana is Google’s name for Gemini’s native image generation and editing capability. In Google’s current model lineup, the exact model id `google/nano-banana` corresponds to the legacy Nano Banana image model, which Google identifies as Gemini 2.5 Flash Image.
Google describes Nano Banana as a conversational image model that can generate, edit, and iterate on visuals using text, images, or a combination of both.
| Developer | |
|---|---|
| Model ID | google/nano-banana |
| Release Date | February 26, 2026 |
| Modalities | Image, Text → Image |
Model identity
Google’s documentation maps Nano Banana to Gemini 2.5 Flash Image, described as the legacy pioneer of the Nano Banana series.
Core function
The model supports conversational image generation and editing from text and image inputs.
Key capabilities
Google says the model can blend multiple images into one image, maintain character consistency, make targeted transformations with natural language, and use Gemini’s world knowledge in image editing.
Availability
Google says the model is available via the Gemini API and Google AI Studio, with enterprise access through Vertex AI.
Position in the lineup
Google’s newer Nano Banana models are Nano Banana 2 Lite, Nano Banana 2, and Nano Banana Pro; Google recommends customers transition away from the legacy Nano Banana model.
Image creation
Generate new images from text prompts or combinations of text and images.
Image editing
Edit existing images conversationally with targeted changes described in natural language.
Multi-image composition
Blend multiple reference images into a single output while preserving consistency across subjects.
Nano Banana 2 Lite
Google describes this as the fastest and cheapest Gemini image model, aimed at speed- and cost-sensitive workloads.
Nano Banana 2
Google describes this as the most versatile general-purpose image model, with strong 4K generation and reliable text rendering.
Nano Banana Pro
Google positions this as the premium model for the most complex visual tasks, with higher world knowledge and advanced localization.
Sources: https://aistudio.google.com/models/nano-banana · https://ai.google.dev/gemini-api/docs/image-generation · https://gemini.google/overview/image-generation/
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Create and edit images conversationally using text, images, video, or a combination, with fine control over the result.
Generate high-quality image content such as detailed, playful, realistic, or whimsical images.
Use it for studio-quality image generation and editing with precise control over visuals.
Build image-based apps and workflows that generate or edit visuals directly inside developer tools and production applications.
import requests r = requests.post( "https://api.aimlapi.com/v1/images/generations", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "google/gemini-2.5-flash-image", "prompt": "A cat holding a sign that says hello" }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/images/generations", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "google/gemini-2.5-flash-image", "prompt": "A cat holding a sign that says hello" }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/images/generations \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"google/gemini-2.5-flash-image","prompt":"A cat holding a sign that says hello"}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Output | |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| Image Editing Arena | 986 | Human preference Elo from blind pairwise comparisons of edited images, measured independently by Artificial Analysis | Source | September 21, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Nano Banana This page | Image generation | |||
| Image generation at scale | ||||
| Image generation at scale |
Nano Banana takes image, text as input and returns image.
Nano Banana became available on February 27, 2026.
Yes, Nano Banana accepts image input as well as a text prompt.
Nano Banana was built by Google.
Send a request to https://api.aimlapi.com/v1/images/generations with google/nano-banana as the model id.
Yes. Nano Banana is served through AI/ML API, so the same key and endpoint format used for other models applies.
Nano Banana is an image generation model, supporting text-to-image and image-to-image modalities.
